Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Falconss1
/
TW-GRPO
like
0
Video-Text-to-Text
Transformers
Safetensors
7 datasets
English
qwen2_5_vl
image-to-text
video-understanding
reasoning
multimodal
reinforcement-learning
question-answering
text-generation-inference
arxiv:
2505.24718
License:
mit
Model card
Files
Files and versions
xet
Community
1
Deploy
Use this model
761d5aa
TW-GRPO
11.7 GB
2 contributors
History:
6 commits
This model has 1 file scanned as unsafe.
Show
files
Falconss1
update model
761d5aa
7 months ago
.gitattributes
1.57 kB
Upload 9 files
7 months ago
README.md
24 Bytes
initial commit
7 months ago
added_tokens.json
605 Bytes
Upload 5 files
7 months ago
chat_template.json
1.05 kB
Upload 5 files
7 months ago
config.json
1.24 kB
Upload 5 files
7 months ago
generation_config.json
317 Bytes
Upload 5 files
7 months ago
merges.txt
1.67 MB
Upload 5 files
7 months ago
model-00001-of-00004.safetensors
4.97 GB
xet
update model
7 months ago
model-00002-of-00004.safetensors
4.99 GB
xet
update model
7 months ago
model-00004-of-00004.safetensors
1.69 GB
xet
Upload model-00004-of-00004.safetensors
7 months ago
model.safetensors.index.json
57.6 kB
Upload 9 files
7 months ago
preprocessor_config.json
575 Bytes
Upload 9 files
7 months ago
special_tokens_map.json
613 Bytes
Upload 9 files
7 months ago
tokenizer.json
11.4 MB
xet
Upload 9 files
7 months ago
tokenizer_config.json
7.3 kB
Upload 9 files
7 months ago
trainer_state.json
209 kB
Upload 9 files
7 months ago
training_args.bin
8.44 kB
xet
Upload 9 files
7 months ago
vocab.json
2.78 MB
Upload 9 files
7 months ago